{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DNGJ47IUFOHB4RATIWMICS42LA","short_pith_number":"pith:DNGJ47IU","schema_version":"1.0","canonical_sha256":"1b4c9e7d142b8e1e44134598814b9a581635422ecd493b70b13f84aa34f0006e","source":{"kind":"arxiv","id":"2605.15618","version":1},"attestation_state":"computed","paper":{"title":"Latent Video Prediction Learns Better World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam, James Bailey, Naveed Akhtar","submitted_at":"2026-05-15T04:59:30Z","abstract_excerpt":"Self-supervised video models are increasingly framed as world models, yet their evaluation remains largely confined to a single top-1 accuracy score on clean benchmarks. This leaves a major gap in comprehending their potential as world models. We present the first systematic study addressing this gap, analyzing four matched-capacity frontier video foundation models, V-JEPA 2.1, V-JEPA 2, VideoPrism, and VideoMAEv2, across five robustness axes relevant to their deployment as video world models: feature discriminability, corruption robustness, fine-grained discrimination, occlusion robustness, a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T04:59:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f7fadab1d1a828f725fb33e1b59a8ecd33a153e7d4ac80743982b13eb5a5429","abstract_canon_sha256":"ce8fa7ae28e3996138c9f04c154072e37d00613cf8957a43e0b9cd54c15f6359"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:08.482881Z","signature_b64":"84I4i8AsEhGfhpbkbmXmbOybAExtR5irGuJfTPvvBoV8v4v+fIyYm3TdvmChrmawYNxQdH5zJ5CoPOEfnnp0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b4c9e7d142b8e1e44134598814b9a581635422ecd493b70b13f84aa34f0006e","last_reissued_at":"2026-05-20T00:01:08.482082Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:08.482082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Video Prediction Learns Better World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam, James Bailey, Naveed Akhtar","submitted_at":"2026-05-15T04:59:30Z","abstract_excerpt":"Self-supervised video models are increasingly framed as world models, yet their evaluation remains largely confined to a single top-1 accuracy score on clean benchmarks. This leaves a major gap in comprehending their potential as world models. We present the first systematic study addressing this gap, analyzing four matched-capacity frontier video foundation models, V-JEPA 2.1, V-JEPA 2, VideoPrism, and VideoMAEv2, across five robustness axes relevant to their deployment as video world models: feature discriminability, corruption robustness, fine-grained discrimination, occlusion robustness, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15618","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15618/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:34.615485Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.039532Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2f4ad5c4a9e414c6305a04d7761ce9c71711b2594c7a5ca2e83cee98d25c4c75"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.15618","created_at":"2026-05-20T00:01:08.482207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15618v1","created_at":"2026-05-20T00:01:08.482207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15618","created_at":"2026-05-20T00:01:08.482207+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNGJ47IUFOHB","created_at":"2026-05-20T00:01:08.482207+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNGJ47IUFOHB4RAT","created_at":"2026-05-20T00:01:08.482207+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNGJ47IU","created_at":"2026-05-20T00:01:08.482207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNGJ47IUFOHB4RATIWMICS42LA","json":"https://pith.science/pith/DNGJ47IUFOHB4RATIWMICS42LA.json","graph_json":"https://pith.science/api/pith-number/DNGJ47IUFOHB4RATIWMICS42LA/graph.json","events_json":"https://pith.science/api/pith-number/DNGJ47IUFOHB4RATIWMICS42LA/events.json","paper":"https://pith.science/paper/DNGJ47IU"},"agent_actions":{"view_html":"https://pith.science/pith/DNGJ47IUFOHB4RATIWMICS42LA","download_json":"https://pith.science/pith/DNGJ47IUFOHB4RATIWMICS42LA.json","view_paper":"https://pith.science/paper/DNGJ47IU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15618&json=true","fetch_graph":"https://pith.science/api/pith-number/DNGJ47IUFOHB4RATIWMICS42LA/graph.json","fetch_events":"https://pith.science/api/pith-number/DNGJ47IUFOHB4RATIWMICS42LA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNGJ47IUFOHB4RATIWMICS42LA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNGJ47IUFOHB4RATIWMICS42LA/action/storage_attestation","attest_author":"https://pith.science/pith/DNGJ47IUFOHB4RATIWMICS42LA/action/author_attestation","sign_citation":"https://pith.science/pith/DNGJ47IUFOHB4RATIWMICS42LA/action/citation_signature","submit_replication":"https://pith.science/pith/DNGJ47IUFOHB4RATIWMICS42LA/action/replication_record"}},"created_at":"2026-05-20T00:01:08.482207+00:00","updated_at":"2026-05-20T00:01:08.482207+00:00"}